DocuMindGPT

DocuMindGPT is a document-grounded Q&A CLI that uses RAG (Retrieval-Augmented Generation) to answer questions based on your PDFs or text files. It features a built-in evaluation agent that scores answers for hallucinations and relevance.

Flowchart

Features

• Ingestion: Chunk, embed, and store documents in Supabase (pgvector).
• RAG Chat: Query your knowledge base using Gemini 2.5 Flash.
• Auto-Evaluation: Every answer is audited by a secondary AI agent for accuracy (Pass/Fail verdict).

Prerequisites

• Python 3.10+
• A Supabase project
• A Google Gemini API Key

Setup

1. Database: Run the contents of setup.sql in your Supabase SQL Editor to enable pgvector and create the required tables.
2. Install Dependencies:

   pip install -r requirements.txt

3. Environment Variables: Create a .env file in the root directory:

   GEMINI_API_KEY=your_google_api_key
   SUPABASE_URL=your_supabase_project_url
   SUPABASE_KEY=your_supabase_anon_key

Usage

1. Upload a Document

Ingest a file (PDF or text) into the vector store.

python main.py upload path/to/document.pdf